[PATCH 0/2] printk.kmsg: Ratelimit it by default

[PATCH 0/2] printk.kmsg: Ratelimit it by default

[Borislav Petkov]

From: Borislav Petkov <bp@suse.de>

Ok, so how about these two?

Rostedt is busy so I took Linus' old patch and Steven's last v2 and
split and extended them with the comments people had on the last thread:

https://lkml.kernel.org/r/20160425145606.598329f2@gandalf.local.home

I hope, at least.

So it is ratelimiting by default, with "on" and "off" cmdline options. I
called the option somewhat a bit shorter too: "printk.kmsg"

The current use cases of this and of which I'm aware are:

* debug the kernel and thus shut up all interfering input from
userspace, i.e. boot with "printk.kmsg=off"

* debug userspace (and by that I mean systemd) by booting with
"printk.kmsg=on" so that the ratelimiting is disabled and the kernel log
gets all the spew.

Thoughts?

Thanks.

Borislav Petkov (2):
  ratelimit: Extend to print suppressed messages on release
  printk: Add kernel parameter to control writes to /dev/kmsg

 Documentation/kernel-parameters.txt |  6 ++++
 include/linux/ratelimit.h           | 36 +++++++++++++++++++----
 kernel/printk/printk.c              | 57 +++++++++++++++++++++++++++++++------
 lib/ratelimit.c                     |  6 ++--
 4 files changed, 90 insertions(+), 15 deletions(-)

-- 
2.7.3

[PATCH 1/2] ratelimit: Extend to print suppressed messages on release

[Borislav Petkov]

From: Borislav Petkov <bp@suse.de>

Extend the ratelimiting facility to print the amount of suppressed lines
when it is being released.

Separated from a previous patch by Linus.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ratelimit.h | 36 +++++++++++++++++++++++++++++++-----
 lib/ratelimit.c           |  6 ++++--
 2 files changed, 35 insertions(+), 7 deletions(-)

diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 18102529254e..a68a56d223c2 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -2,11 +2,15 @@
 #define _LINUX_RATELIMIT_H
 
 #include <linux/param.h>
+#include <linux/sched.h>
 #include <linux/spinlock.h>
 
 #define DEFAULT_RATELIMIT_INTERVAL	(5 * HZ)
 #define DEFAULT_RATELIMIT_BURST		10
 
+/* issue num suppressed message on exit */
+#define RATELIMIT_MSG_ON_RELEASE	BIT(0)
+
 struct ratelimit_state {
 	raw_spinlock_t	lock;		/* protect the state */
 
@@ -15,6 +19,7 @@ struct ratelimit_state {
 	int		printed;
 	int		missed;
 	unsigned long	begin;
+	unsigned long	flags;
 };
 
 #define RATELIMIT_STATE_INIT(name, interval_init, burst_init) {		\
@@ -34,12 +39,33 @@ struct ratelimit_state {
 static inline void ratelimit_state_init(struct ratelimit_state *rs,
 					int interval, int burst)
 {
+	memset(rs, 0, sizeof(*rs));
+
 	raw_spin_lock_init(&rs->lock);
-	rs->interval = interval;
-	rs->burst = burst;
-	rs->printed = 0;
-	rs->missed = 0;
-	rs->begin = 0;
+	rs->interval	= interval;
+	rs->burst	= burst;
+}
+
+static inline void ratelimit_default_init(struct ratelimit_state *rs)
+{
+	return ratelimit_state_init(rs, DEFAULT_RATELIMIT_INTERVAL,
+					DEFAULT_RATELIMIT_BURST);
+}
+
+static inline void ratelimit_state_exit(struct ratelimit_state *rs)
+{
+	if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE))
+		return;
+
+	if (rs->missed)
+		printk(KERN_WARNING "%s: %d callbacks suppressed\n",
+		       current->comm, rs->missed);
+}
+
+static inline void
+ratelimit_set_flags(struct ratelimit_state *rs, unsigned long flags)
+{
+	rs->flags = flags;
 }
 
 extern struct ratelimit_state printk_ratelimit_state;
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 2c5de86460c5..b753f0cfb00b 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -46,12 +46,14 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 		rs->begin = jiffies;
 
 	if (time_is_before_jiffies(rs->begin + rs->interval)) {
-		if (rs->missed)
+		if (rs->missed && !(rs->flags & RATELIMIT_MSG_ON_RELEASE))
 			printk(KERN_WARNING "%s: %d callbacks suppressed\n",
 				func, rs->missed);
 		rs->begin   = jiffies;
 		rs->printed = 0;
-		rs->missed  = 0;
+
+		if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE))
+			rs->missed = 0;
 	}
 	if (rs->burst && rs->burst > rs->printed) {
 		rs->printed++;
-- 
2.7.3

[PATCH 2/2] printk: Add kernel parameter to control writes to /dev/kmsg

[Borislav Petkov]

From: Borislav Petkov <bp@suse.de>

Add a "printk.kmsg" kernel command line parameter which controls how
userspace writes into /dev/kmsg. It has two options:

* on  - unlimited logging from userspace
* off - logging from userspace gets ignored

The default setting is to ratelimit the messages written to it.

It additionally does not limit logging to /dev/kmsg while the system is
booting if we haven't disabled it on the command line.

This patch is based on previous patches from Linus and Steven.

Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/kernel-parameters.txt |  6 ++++
 kernel/printk/printk.c              | 57 +++++++++++++++++++++++++++++++------
 2 files changed, 55 insertions(+), 8 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 82b42c958d1c..4799c88b7258 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3150,6 +3150,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 			default: disabled
 
+	printk.kmsg={on,off}
+			Control writing to /dev/kmsg.
+			on - unlimited logging to /dev/kmsg from userspace
+			off - logging to /dev/kmsg disabled
+			Default: ratelimited logging.
+
 	printk.time=	Show timing data prefixed to each printk message line
 			Format: <bool>  (1/Y/y=enable, 0/N/n=disable)
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 60cdf6386763..33701a166f26 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -86,6 +86,29 @@ static struct lockdep_map console_lock_dep_map = {
 };
 #endif
 
+#define DEVKMSG_LOG_RATELIMIT	0
+#define DEVKMSG_LOG_ON		1
+#define DEVKMSG_LOG_OFF		2
+
+/* DEVKMSG_LOG_RATELIMIT by default */
+static unsigned int __read_mostly devkmsg_log;
+static int __init control_devkmsg(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2))
+		devkmsg_log = DEVKMSG_LOG_ON;
+	else if (!strncmp(str, "off", 3))
+		devkmsg_log = DEVKMSG_LOG_OFF;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+__setup("printk.kmsg=", control_devkmsg);
+
+
 /*
  * Number of registered extended console drivers.
  *
@@ -614,6 +637,7 @@ struct devkmsg_user {
 	u64 seq;
 	u32 idx;
 	enum log_flags prev;
+	struct ratelimit_state rs;
 	struct mutex lock;
 	char buf[CONSOLE_EXT_LOG_MAX];
 };
@@ -623,11 +647,24 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
 	char *buf, *line;
 	int level = default_message_loglevel;
 	int facility = 1;	/* LOG_USER */
+	struct file *file = iocb->ki_filp;
+	struct devkmsg_user *user = file->private_data;
 	size_t len = iov_iter_count(from);
 	ssize_t ret = len;
 
-	if (len > LOG_LINE_MAX)
+	if (!user || len > LOG_LINE_MAX)
 		return -EINVAL;
+
+	/* Ignore when user logging is disabled. */
+	if (devkmsg_log == DEVKMSG_LOG_OFF)
+		return len;
+
+	/* Ratelimit when not explicitly enabled or when we're not booting. */
+	if ((system_state != SYSTEM_BOOTING) && (devkmsg_log != DEVKMSG_LOG_ON)) {
+		if (!___ratelimit(&user->rs, current->comm))
+			return ret;
+	}
+
 	buf = kmalloc(len+1, GFP_KERNEL);
 	if (buf == NULL)
 		return -ENOMEM;
@@ -801,18 +838,20 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 	int err;
 
 	/* write-only does not need any file context */
-	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
-		return 0;
-
-	err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
-				       SYSLOG_FROM_READER);
-	if (err)
-		return err;
+	if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
+		err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
+					       SYSLOG_FROM_READER);
+		if (err)
+			return err;
+	}
 
 	user = kmalloc(sizeof(struct devkmsg_user), GFP_KERNEL);
 	if (!user)
 		return -ENOMEM;
 
+	ratelimit_default_init(&user->rs);
+	ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE);
+
 	mutex_init(&user->lock);
 
 	raw_spin_lock_irq(&logbuf_lock);
@@ -831,6 +870,8 @@ static int devkmsg_release(struct inode *inode, struct file *file)
 	if (!user)
 		return 0;
 
+	ratelimit_state_exit(&user->rs);
+
 	mutex_destroy(&user->lock);
 	kfree(user);
 	return 0;
-- 
2.7.3

Re: [PATCH 2/2] printk: Add kernel parameter to control writes to /dev/kmsg

[Ingo Molnar]

* Borislav Petkov <bp@alien8.de> wrote:

> From: Borislav Petkov <bp@suse.de>
> 
> Add a "printk.kmsg" kernel command line parameter which controls how
> userspace writes into /dev/kmsg. It has two options:
> 
> * on  - unlimited logging from userspace
> * off - logging from userspace gets ignored

Please also add a sysctl!

I *so* want to enable this on distro kernels without having to reboot the 
kernel...

Thanks,

	Ingo

Re: [PATCH 2/2] printk: Add kernel parameter to control writes to /dev/kmsg

[Steven Rostedt]

On Tue, 14 Jun 2016 12:21:35 +0200
Ingo Molnar <mingo@kernel.org> wrote:

> * Borislav Petkov <bp@alien8.de> wrote:
> 
> > From: Borislav Petkov <bp@suse.de>
> > 
> > Add a "printk.kmsg" kernel command line parameter which controls how
> > userspace writes into /dev/kmsg. It has two options:
> > 
> > * on  - unlimited logging from userspace
> > * off - logging from userspace gets ignored  
> 
> Please also add a sysctl!
> 
> I *so* want to enable this on distro kernels without having to reboot the 
> kernel...
> 

But can we make it a one way feature (or a kernel parameter to do so?)
that will prevent userspace from enabling it after it's been disabled.

-- Steve

Re: [PATCH 2/2] printk: Add kernel parameter to control writes to /dev/kmsg

[Borislav Petkov]

On Tue, Jun 14, 2016 at 02:14:56PM -0400, Steven Rostedt wrote:
> But can we make it a one way feature (or a kernel parameter to do so?)
> that will prevent userspace from enabling it after it's been disabled.

You mean to be able to do boot with:

"printk.kmsg=off_and_i_mean_it"

which then disables the sysctl? Are you suspecting insolent userspace
reenabling it?

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.

Re: [PATCH 2/2] printk: Add kernel parameter to control writes to /dev/kmsg

[Linus Torvalds]

On Tue, Jun 14, 2016 at 8:14 AM, Steven Rostedt <rostedt@goodmis.org> wrote:
>>
>> Please also add a sysctl!
>>
>> I *so* want to enable this on distro kernels without having to reboot the
>> kernel...
>>
>
> But can we make it a one way feature (or a kernel parameter to do so?)
> that will prevent userspace from enabling it after it's been disabled.

Possibly we could just say that if a kernel command line option has
been given, that is absolute.

And then a sysctl for when you do *not* explicitly set if on the
kernel command line?

             Linus

Re: [PATCH 2/2] printk: Add kernel parameter to control writes to /dev/kmsg

[Borislav Petkov]

On Wed, Jun 15, 2016 at 03:40:04PM -1000, Linus Torvalds wrote:
> Possibly we could just say that if a kernel command line option has
> been given, that is absolute.
> 
> And then a sysctl for when you do *not* explicitly set if on the
> kernel command line?

Ok, how about this ontop?

It is only lightly tested in a vm but basically I'm using the second
byte of devkmsg_log to set a bit in there and the sysctl handler looks
at it.

It is also visible in sysctl and we know it has been cmdline-disabled:

$ cat /proc/sys/kernel/printk_kmsg
256

---
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index a3683ce2a2f3..02fe4562953f 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -752,6 +752,19 @@ send before ratelimiting kicks in.
 
 ==============================================================
 
+printk_kmsg:
+
+Control the logging to /dev/kmsg from userspace:
+
+0: default, ratelimited
+1: unlimited logging to /dev/kmsg from userspace
+2: logging to /dev/kmsg disabled
+
+The kernel command line parameter printk.kmsg= overrides this setting
+and once set, it cannot be changed by this sysctl interface anymore.
+
+==============================================================
+
 randomize_va_space:
 
 This option can be used to select the type of process address
diff --git a/include/linux/printk.h b/include/linux/printk.h
index f4da695fd615..bcf72e756122 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -171,6 +171,12 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 extern int printk_delay_msec;
 extern int dmesg_restrict;
 extern int kptr_restrict;
+extern unsigned int devkmsg_log;
+
+struct ctl_table;
+
+int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
+			      void __user *buffer, size_t *lenp, loff_t *ppos);
 
 extern void wake_up_klogd(void);
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 33701a166f26..9f0a885c2718 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -86,12 +86,15 @@ static struct lockdep_map console_lock_dep_map = {
 };
 #endif
 
-#define DEVKMSG_LOG_RATELIMIT	0
-#define DEVKMSG_LOG_ON		1
-#define DEVKMSG_LOG_OFF		2
+#define DEVKMSG_LOG_RATELIMIT		0
+#define DEVKMSG_LOG_ON			1
+#define DEVKMSG_LOG_OFF			2
+#define DEVKMSG_LOCK			(1 << 8)
+#define DEVKMSG_LOG_MASK		(DEVKMSG_LOCK - 1)
+#define DEVKMSG_LOCKED_MASK		~DEVKMSG_LOG_MASK
 
 /* DEVKMSG_LOG_RATELIMIT by default */
-static unsigned int __read_mostly devkmsg_log;
+unsigned int __read_mostly devkmsg_log;
 static int __init control_devkmsg(char *str)
 {
 	if (!str)
@@ -101,14 +104,30 @@ static int __init control_devkmsg(char *str)
 		devkmsg_log = DEVKMSG_LOG_ON;
 	else if (!strncmp(str, "off", 3))
 		devkmsg_log = DEVKMSG_LOG_OFF;
+	else if (!strncmp(str, "ratelimit", 9))
+		devkmsg_log = DEVKMSG_LOG_RATELIMIT;
 	else
 		return -EINVAL;
 
+	/* Sysctl cannot change it anymore. */
+	devkmsg_log |= DEVKMSG_LOCK;
+
 	return 0;
 }
 __setup("printk.kmsg=", control_devkmsg);
 
 
+int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
+			      void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (devkmsg_log & DEVKMSG_LOCKED_MASK) {
+		if (write)
+			return -EINVAL;
+	}
+
+	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+}
+
 /*
  * Number of registered extended console drivers.
  *
@@ -656,11 +675,12 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
 		return -EINVAL;
 
 	/* Ignore when user logging is disabled. */
-	if (devkmsg_log == DEVKMSG_LOG_OFF)
+	if ((devkmsg_log & DEVKMSG_LOG_MASK) == DEVKMSG_LOG_OFF)
 		return len;
 
 	/* Ratelimit when not explicitly enabled or when we're not booting. */
-	if ((system_state != SYSTEM_BOOTING) && (devkmsg_log != DEVKMSG_LOG_ON)) {
+	if ((system_state != SYSTEM_BOOTING) &&
+	    ((devkmsg_log & DEVKMSG_LOG_MASK) != DEVKMSG_LOG_ON)) {
 		if (!___ratelimit(&user->rs, current->comm))
 			return ret;
 	}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 87b2fc38398b..a29d6c4fa86c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -814,6 +814,15 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &ten_thousand,
 	},
 	{
+		.procname	= "printk_kmsg",
+		.data		= &devkmsg_log,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= devkmsg_sysctl_set_loglvl,
+		.extra1		= &zero,
+		.extra2		= &two,
+	},
+	{
 		.procname	= "dmesg_restrict",
 		.data		= &dmesg_restrict,
 		.maxlen		= sizeof(int),

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.

Re: [PATCH 0/2] printk.kmsg: Ratelimit it by default

[Linus Torvalds]

On Tue, Jun 14, 2016 at 12:12 AM, Borislav Petkov <bp@alien8.de> wrote:
>
> Ok, so how about these two?

Looks ok to me. Ack.

              Linus